Deep Learning Data Privacy Protection Based on Homomorphic Encryption in AIoT

<table class="table-group" id="tab3"><tr><td><table class="table"><tr><td class="thead-hr" colspan="6"><hr/></td></tr><tr><td class="align_left">Key length</td><td class="align_center">512</td><td class="align_center">768</td><td class="align_center">1024</td><td class="align_center">2048</td><td class="align_center">3072</td></tr><tr><td class="align_left">1 sample</td><td class="align_center">0.281</td><td class="align_center">0.589</td><td class="align_center">1.163</td><td class="align_center">7.707</td><td class="align_center">24.399</td></tr><tr><td class="align_left">64 sample(s)</td><td class="align_center">13.175</td><td class="align_center">35.506</td><td class="align_center">72.886</td><td class="align_center">462.563</td><td class="align_center">1510.263</td></tr><tr class="table-tr"><td colspan="6"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>The influence of key length on the efficiency of sample encryption and decryption.</div>

Mobile Information Systems

tab3

Table 3

Table 3: Deep Learning Data Privacy Protection Based on Homomorphic Encryption in AIoT 